state: generation 5149 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T11:48:58.707806+00:00",
|
||||
"lastSyncTime": "2026-09-10T11:48:57.307255+00:00",
|
||||
"generatedAt": "2026-09-10T11:57:54.886814+00:00",
|
||||
"lastSyncTime": "2026-09-10T11:57:54.623286+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1494,30 +1494,30 @@
|
||||
"unresolvedFailureCount": 31
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 24,
|
||||
"decisionFailureRate": 0.96,
|
||||
"decisionSuccessRate": 0.04,
|
||||
"decisionTotal": 25,
|
||||
"attributableFailureCount": 25,
|
||||
"decisionFailureRate": 0.9615,
|
||||
"decisionSuccessRate": 0.0385,
|
||||
"decisionTotal": 26,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 26,
|
||||
"backend_operator": 2,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 77,
|
||||
"failureRate": 0.9872,
|
||||
"failureCount": 78,
|
||||
"failureRate": 0.9873,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0128,
|
||||
"successRate": 0.0127,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 78,
|
||||
"total": 79,
|
||||
"unresolvedFailureCount": 53
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
@@ -2291,13 +2291,13 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 121,
|
||||
"decisionFailureRate": 0.716,
|
||||
"decisionSuccessRate": 0.284,
|
||||
"decisionTotal": 169,
|
||||
"attributableFailureCount": 122,
|
||||
"decisionFailureRate": 0.7176,
|
||||
"decisionSuccessRate": 0.2824,
|
||||
"decisionTotal": 170,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 115,
|
||||
"backend_operator": 2,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 87,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 24,
|
||||
@@ -2305,14 +2305,14 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 965,
|
||||
"failureRate": 0.9526,
|
||||
"failureCount": 966,
|
||||
"failureRate": 0.9527,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0474,
|
||||
"total": 1013,
|
||||
"successRate": 0.0473,
|
||||
"total": 1014,
|
||||
"unresolvedFailureCount": 844
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T11:48:58.703511+00:00",
|
||||
"generatedAt": "2026-09-10T11:57:54.880413+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2494,27 +2494,27 @@
|
||||
"unresolvedFailureCount": 218
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 25,
|
||||
"decisionFailureRate": 0.9615,
|
||||
"decisionSuccessRate": 0.0385,
|
||||
"decisionTotal": 26,
|
||||
"attributableFailureCount": 26,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 27,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 26,
|
||||
"backend_operator": 2,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 78,
|
||||
"failureRate": 0.9873,
|
||||
"failureCount": 79,
|
||||
"failureRate": 0.9875,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0127,
|
||||
"total": 79,
|
||||
"successRate": 0.0125,
|
||||
"total": 80,
|
||||
"unresolvedFailureCount": 53
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -4060,31 +4060,31 @@
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 4,
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8571,
|
||||
"decisionSuccessRate": 0.1429,
|
||||
"decisionTotal": 7,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"backend_operator": 2,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureRate": 0.9412,
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.9444,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T09:20:50.207399+00:00",
|
||||
"lastTerminalAt": "2026-09-10T11:57:54.623286+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0588,
|
||||
"successRate": 0.0556,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -7002,16 +7002,16 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1569,
|
||||
"totalRecords": 1656,
|
||||
"terminalRecords": 1570,
|
||||
"totalRecords": 1657,
|
||||
"totals": {
|
||||
"attributableFailureCount": 410,
|
||||
"decisionFailureRate": 0.8894,
|
||||
"decisionSuccessRate": 0.1106,
|
||||
"decisionTotal": 461,
|
||||
"attributableFailureCount": 411,
|
||||
"decisionFailureRate": 0.8896,
|
||||
"decisionSuccessRate": 0.1104,
|
||||
"decisionTotal": 462,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 337,
|
||||
"backend_operator": 34,
|
||||
"backend_operator": 35,
|
||||
"framework_architecture_unsupported": 271,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 46,
|
||||
@@ -7022,21 +7022,21 @@
|
||||
"参数/模板问题": 95,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1518,
|
||||
"failureCount": 1519,
|
||||
"failureRate": 0.9675,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 51,
|
||||
"successRate": 0.0325,
|
||||
"total": 1569,
|
||||
"total": 1570,
|
||||
"unresolvedFailureCount": 1105
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -7044,7 +7044,7 @@
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7065,6 +7065,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1656,
|
||||
"summarizedRecords": 1657,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user